Metaphor Audit · Discourse Depot

Emotional intelligence in large language models is fragmented across perception, cognition, and interaction

Anthropomorphism audit, explanation framing, and accountability architecture. by Minghao Lv, Lu Chen, Enchang Zhang, Anji Zhou, Xiaoran Xue, Hanyi Zhang, Fenghua Tang, Zhuo Rachel Han, Mengyue Wu · 2026-05-23 · article.

Read source arxiv.org

Overview

Headline metrics and distribution of explanatory framing across the analyzed text.

Metaphor Audit

Anthropomorphic frames identified in the text, with acknowledgment status and actor visibility.

Source → Target Mappings

Conceptual mappings drawn from the text and what each mapping conceals.

Explanation Audit

Browse how/why explanatory framing in each passage. Mechanistic ("how") explanations describe processes; agential ("why") explanations attribute purpose, intent, or reasons.

Reframings

Each anthropomorphic passage rewritten in mechanistic language, with the technical reality and (where applicable) the human agency the original obscured.

Critical Analysis

Synthesis across the corpus of identified metaphors and explanations. The conclusion frames the overall argument; critical observations probe specific dimensions.